Notes on healthcare AI, embedded systems, machine learning, graph data, and the engineering behind them.
Production voice-AI has converged on a pattern: graph-based conversations, separated decision and response prompts, synthetic-call regression testing, and per-component latency budgets. Why the stack looks the way it does — and what most teams are still missing.
Everyone keeps announcing the death of prompt engineering. They are describing the symptom, not the shift. The loops you used to run by hand — refine, retry, verify, learn — moved out of your head and into infrastructure. Four of them, simultaneously.
Palantir built a company on the idea that software alone isn't enough: you need engineers embedded with customers. That model has a name, a cost, and a hidden technical debt time bomb most B2B companies are quietly sitting on.
Most healthcare AI companies are failing for the same reason. The ones winning are running the same playbook: one Palantir figured out before anyone called it AI. Forward-deployed engineer. Ontology. Integrations. Then AI tooling.
I built a tool that turns GitHub issues into pull requests using a three-agent pipeline. That's the boring part. The interesting part is what happens when you stop thinking about AI agents as productivity tools and start thinking about them as a workforce, and build a world for them to live in.
Mirth democratized healthcare integration. Then NextGen acquired it, and the world moved on. What the next generation of integration tooling looks like, and why the transition was inevitable.
